Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1339 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.7501. Min Act: -0.0000

Data Index: 499976 (The Pile)

Max Activating Token Index: 833

Text #1

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.7360. Min Act: -0.0000

Data Index: 256972 (The Pile)

Max Activating Token Index: 297

Text #2

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1078448 (The Pile)

Max Activating Token Index: 132

Text #3

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1667546 (The Pile)

Max Activating Token Index: 822

Text #4

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1508023 (The Pile)

Max Activating Token Index: 159

Text #5

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.6472. Min Act: -0.0000

Data Index: 1409077 (The Pile)

Max Activating Token Index: 387

Text #6

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1451686 (The Pile)

Max Activating Token Index: 297

Text #7

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1233799 (The Pile)

Max Activating Token Index: 801

Text #8

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1222919 (The Pile)

Max Activating Token Index: 813

Text #9

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.5231. Min Act: -0.0000

Data Index: 1491342 (The Pile)

Max Activating Token Index: 481

Text #10

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.5588. Min Act: -0.0000

Data Index: 47368 (The Pile)

Max Activating Token Index: 955

Text #11

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4635. Min Act: -0.0000

Data Index: 197050 (The Pile)

Max Activating Token Index: 1022

Text #12

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.7104. Min Act: -0.0000

Data Index: 1359957 (The Pile)

Max Activating Token Index: 847

Text #13

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.5232. Min Act: -0.0000

Data Index: 1701515 (The Pile)

Max Activating Token Index: 959

Text #14

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1798359 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4391. Min Act: -0.0000

Data Index: 112952 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4991. Min Act: -0.0000

Data Index: 481005 (The Pile)

Max Activating Token Index: 99

Text #17

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.5595. Min Act: -0.0000

Data Index: 656716 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4603. Min Act: -0.0000

Data Index: 872389 (The Pile)

Max Activating Token Index: 95

Text #19

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.5018. Min Act: -0.0000

Data Index: 326022 (The Pile)

Max Activating Token Index: 153